5 papers
Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning
Sebastian Sanokowski, Kaustubh Patil
Diffusion models excel at sampling from complex, unnormalized distributions. In this work, we extend Maximum Entropy Reinforcement Learning (ME-RL) to diffusion processes, enabling…
Rethinking Losses for Diffusion Bridge Samplers
Sebastian Sanokowski, Lukas Gruber, Christoph Bartmann +2
Diffusion bridges are a promising class of deep-learning methods for sampling from unnormalized distributions. Recent works show that the Log Variance (LV) loss consistently outper…
A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization
Sebastian Sanokowski, Sepp Hochreiter, Sebastian Lehner
Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combin…
Geometry-Informed Neural Networks
Arturs Berzins, Andreas Radler, Eric Volkmann +3
Geometry is a ubiquitous tool in computer graphics, design, and engineering. However, the lack of large shape datasets limits the application of state-of-the-art supervised learnin…
Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics
Sebastian Sanokowski, Wilhelm Berghammer, Martin Ennemoser +3
Learning to sample from complex unnormalized distributions over discrete domains emerged as a promising research direction with applications in statistical physics, variational inf…